Integrating BC & GC Models In Computing Stereo Disparity As Markov Random Field

Abstract

Belief propagation and graph cuts have emerged as powerful tools for computing efficient approximate solution to stereo disparity field modelled as the Markov random field (MRF). These algorithms have provided the best performance based on results on a standard data set. However, employment of the brightness constancy (BC) assumption severely limits the range of their applications. Previously, augmenting the BC with gradient constancy (GC) assumption has shown to produce a more robust optical flow algorithm. In this paper, these constraints are integrated within the MRF framework to devise an enhanced global method that broadens the application domains for stereo computation. Results of experiments with both semi-synthetic data and more challenging ocean images are presented to illustrate that the proposed method generally outperforms earlier dense optical flow and stereo algorithms.